computer-vision-2

2D Semantic Segmentation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in 2d-semantic-segmentation-2

Trend

Dataset

Best Model

Actions

Deep Indices

xBD

Time Series Prediction Benchmarks

Libraries

i

Use these libraries to find 2d-semantic-segmentation-2 models and implementations

Datasets

xBD

Subtasks

Image Segmentation Text Style Transfer Scene Parsing Reflection Removal Reflection Removal

Most implemented papers

xBD: A Dataset for Assessing Building Damage from Satellite Imagery

Ritwik Gupta, B. Goodman, N. Patel, Richard Hosfelt, Sandra Sajeev, Eric T. Heim, Jigar Doshi, Keane Lucas, H. Choset, Matthew E. Gaston•Wed Nov 20 2019

xBD provides pre- and post-event multi-band satellite imagery from a variety of disaster events with building polygons, classification labels for damage types, ordinal labels of damage level, and corresponding satellite metadata, and will be the largest building damage assessment dataset to date.

334

Content

Extended heartSeg

GF-PA66 3D XCT

WaterScenes

WorldFloods

CamVid

Cityscapes val

SpaceNet 7

WaterScenes

CaDIS

DeepSport Dataset

Foreground Segmentation

Human Part Segmentation

Continual Semantic Segmentation

Material Segmentation

All-day Semantic Segmentation

Burned Area Delineation

Landmark-based segmentation

Intention-oriented Segmentation

0

Paper Graph

Realtime Global Attention Network for Semantic Segmentation

Xi Mo, Xiangyu Chen•Thu Dec 23 2021

An end-to-end realtime global attention neural network (RGANet) for the challenging task of semantic segmentation and an improved evaluation metric, namely MGRID, is proposed to alleviate the negative effect of non-convex, widely scattered ground-truth areas.

2 0

Paper Graph

SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks

Serdar Erişen•Sat Jan 27 2024

This research proposes an encoder-decoder architecture with a unique efficient residual network, Efficient-ResNet, developed with the additional attention-fusion networks (AfNs) inspired by AbM to improve the efficiency in the one-to-one conversion of the semantic information.

21 0

Paper Graph

See and Think: Disentangling Semantic Scene Completion

Yiming Zeng, Shice Liu, Yu Hu, Qiankun Tang, Beibei Jin, Yinhe Han, Xiaowei Li•Sun Dec 31 2017

Experimental results show that regardless of inputing a single depth or RGB-D, the proposed disentangled framework can generate high-quality semantic scene completion, and outperforms state-of-the-art approaches on both synthetic and real datasets.

109 0

Paper Graph

3D-MiniNet: Learning a 2D Representation From Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation

A. C. Murillo, L. Montesano, Iñigo Alonso, L. Riazuelo•Mon Feb 24 2020

3D-MiniNet is presented, a novel approach for LIDAR semantic segmentation that combines 3D and 2D learning layers that first learns a 2D representation from the raw points through a novel projection which extracts local and global information from the 3D data.

152 0

Paper Graph

Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusion

Ethan Weber, Hassan Kané•Sat Apr 11 2020

Findings on problem framing, data processing and training procedures which are specifically helpful for the task of building damage assessment using the newly released xBD dataset are reported.

114 0

Paper Graph

SofGAN: A Portrait Image Generator with Dynamic Styling

Hao Su, Jingyi Yu, Anpei Chen, Ling Xie, Ruiyang Liu, Zhang Chen•Mon Jul 06 2020

A SofGAN image generator to decouple the latent space of portraits into two subspaces: a geometry space and a texture space and it is shown that the system can generate high-quality portrait images with independently controllable geometry and texture attributes.

90 0

Paper Graph

Virtual Multi-view Fusion for 3D Semantic Segmentation

T. Funkhouser, C. Pantofaru, David A. Ross, Abhijit Kundu, A. Fathi, Xiaoqi Yin, B. Brewington•Sat Jul 25 2020

This paper revisits the classic multiview representation of 3D meshes and study several techniques that make them effective for 3D semantic segmentation of meshes and shows that the virtual views enable more effective training of 2D semantic segmentsation networks than previous multIView approaches.

180 0

Paper Graph

Adding a benchmark result helps the community track progress.